Question

A GenAI engineer has registered a RAG chain in Unity Catalog Model Registry as 'catalog.schema.support_bot' with several versions. The team wants their Model Serving endpoint to always point to the version that has passed QA validation, without editing the endpoint configuration each time a new validated version is created. What is the recommended MLflow approach to accomplish this?

Accepted Answer

Assign a model alias (e.g., 'champion') to the validated version and configure the serving endpoint to serve that alias, updating the alias when a new version passes QA.

Answer

Delete all older model versions so the endpoint automatically serves the only remaining version.

Answer

Hardcode the specific version number in the endpoint config and redeploy the endpoint each time QA validates a new version.

Answer

Use MLflow tags on each run and configure the endpoint to resolve the model by tag key at request time.